© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 5538
    Prev
    Next
    INDEX
    Explanations

    names of individuals in leadership positions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "chief of" followed by a person's title or position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pim
    -0.66
    dayName
    -0.66
     ticking
    -0.65
     additives
    -0.63
     Rept
    -0.61
     predicate
    -0.60
     partName
    -0.60
    ERE
    -0.59
     predic
    -0.58
     detain
    -0.57
    POSITIVE LOGITS
    warts
    0.79
     Athletic
    0.73
    icial
    0.68
    staff
    0.67
    orney
    0.66
    inence
    0.66
     Operations
    0.65
    iple
    0.65
    itan
    0.65
    venture
    0.65
    Activations Density 0.065%

    No Known Activations